22 datasets found

Chest X-ray dataset used for detecting shortcuts in medical images

The dataset used for lung cancer diagnostic task

BloodMNIST is a medical imaging dataset containing 9,000 images of blood samples, each with a size of 224x224x3.

RetinaMNIST is a medical imaging dataset containing 5,000 images of retinal scans, each with a size of 224x224x3.

DermaMNIST is a medical imaging dataset containing 7,000 images of skin lesions, each with a size of 224x224x3.

PathMNIST is a medical imaging dataset containing 9,000 images of breast cancer tissue, each with a size of 224x224x3.

A variety of pre-trained ViT (DINO, DINOv2, SAM, CLIP) and SD models, trained exclusively on natural images, for solving the correspondence problems on medical images.

A hospital-scale chest X-ray database, namely “ChestX-ray8”, which comprises 108,948 frontal-view X-ray images of 32,717 unique patients with the text-mined eight common disease...

The BraTS-2017 and ISLES-2015 segmentation benchmarks

The BreastMNIST dataset is a breast ultrasound dataset for breast cancer detection.

Retinal fundus images have been extensively used for clinical analysis of various ocular diseases, but the quality of fundus images is critical to the diagnosis and screening of...

COVID-19 pandemic has spread rapidly and caused a shortage of global medical resources. The efficiency of COVID-19 diagnosis has become highly significant.

COVID-FL is a real-world medical FL dataset containing 20,055 medical images, sourced from 12 hospitals.

Anomaly detection is the process of identifying atypical data samples that significantly deviate from the majority of the dataset. In the realm of clinical screening and...

The dataset used in the paper is a collection of medical images of patients diagnosed with glioblastoma multiforme, which is a type of brain cancer.

The dataset used in the paper is a collection of medical images of patients diagnosed with glioblastoma multiforme, which is a type of brain cancer.

The dataset used for the diabetic retinopathy diagnosis and uncertainty quantification task.

The EyePACS dataset consists of 35,126 training images and 53,576 testing images only containing grading labels.

MIMIC-III is a large, publicly available clinical database containing information from the Medical Information Mart for Intensive Care III. It is used for various clinical...

The dataset used in this study consists of 25 sequences of CT images of patients affected by abdominal aortic aneurysm.